Ask what was decided. See the sentence it came from.
Meetings, Slack, GitHub and Jira, all in one place: one memory for each project. Everyone on the project asks the same chat, and every answer carries the quote and the source behind it.
- Your own Anthropic key, no markup
- Your client can join the same chat
- A source on every answer
- Claude
- Claude Code
- Cursor
- VS Code
01 Learns from
Everything your project already says, kept
Connect a source once. What was said there becomes memory anyone on the project can ask about, each entry holding the sentence it came from.
What it reads
- Slack: Channels where the team talks it through
- GitHub: Pull requests, issues and reviews
- Google Meet: Meetings, transcribed for you
- Jira: Tickets and what changed on them
- Meeting recordings: Calls recorded right in the app
- Documents: Specs, briefs and contracts
- Your own apps: Anything your own tools send
What it keeps
- Decisions: with the sentence it came from
- Who thinks what: who argued for what, and when
- Action items: who owes what, and by when
- Open questions: what nobody has answered yet
- Risks: what could go wrong, raised early
02 Who asks
One memory, a different question from everyone
The people on a project need different things from it. Each of them asks in plain words and gets an answer built only from what they are allowed to see.
- CEOLeadership only
“Are we still on track for the 17 November launch?”
Answer cites:Leadership sync · 18 Sept
- Project managerTeam only
“What did we promise Lumen about split bills?”
Answer cites:Lumen weekly call · 22 Sept
- DesignerTeam only
“Why does the passcode fallback get its own screen?”
Answer cites:Design review · 14 Aug
- DeveloperTeam only
“What has to be merged before code freeze?”
Answer cites:PR #331 · GitHub
- QATeam only
“What changed since build 412?”
Answer cites:LUM-221 · Jira
- ClientClient can see
“When can our staff start testing the new onboarding?”
Answer cites:#lumen-shared · Slack
03 How it answers
The same question. A different answer for the client, the developer and the CEO. All of them true.
Corvin Labs is building a banking app for its client Lumen. Split bills moved to phase 2, the change request is still unsigned, and the client is in the same chat as the team.
What did we decide about split bills?
It's not in the launch scope. Vlad and Tudor sized it at about 11 dev days plus 3 QA days, which doesn't fit before code freeze on 3 November.
So it's planned for phase 2, right after launch, and Daniel accepted that as long as it comes in the first update after launch.
Daniel's answer is not the model being careful. His search cannot reach those rows at all: who sees what is a Postgres policy, checked before anything is sent to the model.
04 How it works
From a meeting to an answer you can check
What goes in, what memory keeps, how you ask, and what is still owed.
05 See it work
Two things it does on its own
Filmed in the real app, on a demo studio and its client. Nobody clicks anything in either one.
A Slack message becomes a card on the board
Ioana asks Tudor in Slack to build a screen by Friday. InteliLang reads who, what and by when, puts the card on Tudor's board, keeps the message it came from, and tells him.
A client call updates the whole project
Ioana records the weekly call with Lumen. Seconds later the decisions, the new risk and five to-dos are in memory, the old plan is marked as replaced, and the cards are on the right boards.
06 Under the hood
Built to be trusted with a project’s memory
The parts nobody sees in a demo, and the first things a company asks about.
- RLS
Who sees what is enforced by the database
Postgres row-level security checks every query, so a client never reaches a team-only row, not even by mistake.
- No training
Never used to train AI
Your project's content goes to Anthropic only to answer your team's questions, on your own key, and is never used to train a model.
- EN · RO
English and Romanian
The whole app is in both languages, and anyone can ask in the one they think in.
- Your schedule
Old content deletes itself
Each company chooses how long things are kept. A nightly job removes the rest, without anyone remembering to.
- Activity log
Every sensitive change is logged
Keys, people, roles, sources, sharing and retention changes are recorded with who made them and when.
- Encrypted
Keys and tokens stay sealed
Anthropic keys and connector tokens are encrypted at rest, never logged and never sent to the browser.
07 Where to use it
Ask it from the tools you already use
Open InteliLang in the browser, or ask the same project memory from Claude, Claude Code, Cursor or VS Code without switching windows.
InteliLang on the web
The whole app: the chat, memory, the board and files, for everyone on the project, including your client.
Who pays for the AI: Your company's Anthropic key, at Anthropic's price
Claude
Add InteliLang as a connector in Claude on the web, desktop or phone, then ask about a project in the middle of any conversation.
Who pays for the AI: Your own Claude plan
Claude Code
Connect it with one command and a personal key. Check what was decided before you write the code for it.
Who pays for the AI: The account you use Claude Code with
Cursor and VS Code
Paste a few lines into the editor's MCP settings, and its assistant can read the project's decisions next to your code.
Who pays for the AI: The editor's own AI
Every way in sees only what you can see on that project. A personal key can be revoked in one click, and the app it connected stops right away.
08 Numbers
Numbers we hold ourselves to
No customer counts and no made-up benchmarks. Just how the product is built to spend your money.
- Markup on AI. You pay Anthropic's price, on your own key.
- 0%
- Off reading large imports and backfills, through Anthropic's batch pricing.
- 50%
- For a question the project has already answered.
- $0
- Levels of who can see what: the client, the team and leadership.
- 3
09 Who it's for
Made for small and mid-sized teams
Studios, agencies and product teams that work in projects, often with the client in the same conversation. It is not trying to be a search engine for a company of ten thousand.
Running in an afternoon
Create a company, paste your Anthropic key, then connect a Slack channel or record a meeting. No sales call, no rollout project.
The AI costs what Anthropic charges
It runs on your own key, billed by Anthropic with no markup from us. A question the project has already answered costs nothing.
Bring your client in
Invite them as a guest. They ask the same chat and get true answers, built only from what they are allowed to see.
It tidies up after itself
Old meetings and messages are deleted on the schedule you choose, so the memory stays current and nothing lingers.
10 Pricing
Free while we're in early access
Every feature, for your whole team and your clients. No card, no trial running out.
€0per month
Paid plans will come later, priced per company and never per person.
Start for freeEverything is included
- As many people on your team as you need
- Your clients, invited as guests
- Unlimited projects
- Slack, GitHub, Jira, meetings and documents
- Keep what it remembers for as long as you choose
The AI runs on your own Anthropic key, so Anthropic bills you directly for what it uses, with no markup from us. A question the project has already answered costs nothing.
11 Questions
Questions people ask before they start
What it is, what it learns from, who sees what, and what it costs.
Put one project in and ask it something you already know the answer to.
Connect a Slack channel, a repository or one recorded meeting, then ask it something you already know the answer to. The answer should come back with the quote you were thinking of, and the source next to it.